hadoop-job(mapReducer计算单词出现的个数)

1.============map===============

package com.it18zhang.hadoop.mr;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * Mapper
 */
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    /**
     * key : 行首偏移量，字节数，意义不大。
     * value ： 一行文本
     */
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //
        String line = value.toString() ;
        String[] arr = line.split(" ");

        Text keyOut = new Text() ;
        IntWritable valueOut = new IntWritable(1) ;
        for(String word : arr){
            keyOut.set(word);
            context.write(keyOut,valueOut);
        }
    }
}

2.============refucer===============

package com.it18zhang.hadoop.mr;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

/**
 * reducer
 */
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    /**
     * key : word
     * values : 该key下聚合的value
     */
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int count = 0 ;
        for(IntWritable iw : values){
            count = count + iw.get() ;
        }
        context.write(key , new IntWritable(count));
    }
}

3.============统计===============

package com.it18zhang.hadoop.mr;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;
public class App {
    public static void main(String[] args) throws Exception {
        if(args == null || args.length<2){
            throw new Exception("参数不足，需要2个参数");
        }
        Configuration conf = new Configuration();
        FileSystem fs = FileSystem.get(conf);
        //递归删除输出目录
        fs.delete(new Path(args[1]),true);

        //创建一个作业
        Job job = Job.getInstance(conf);
        //调用job方法 名字随便期（word_count_add ）
        job.setJobName("word_count_add");
        //获取类的路径
        job.setJarByClass(App.class);

//        //需要计算的文件路径
//        FileInputFormat.addInputPath(job,new Path("file:///Users/yangyanqing/godev/wc"));
//        //计算后文件输出
//        FileOutputFormat.setOutputPath(job,new Path("file:///Users/yangyanqing/godev/wc/out"));
        //需要计算的文件路径
        FileInputFormat.addInputPath(job,new Path(args[0]));
        //计算后文件输出
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        //设置mapper类和reducer类
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        //输出mapper类和reducer类的类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class );
        //设置readuce个数
        job.setNumReduceTasks(1);
        //开始作业
        job.waitForCompletion(true);
    }
}

巴特西

hadoop-job(mapReducer计算单词出现的个数)

最新文章

热门文章